Development of an exchange-correlation functional with uncertainty quantification capabilities for density functional theory

Development of an exchange-correlation functional with uncertainty quantification capabilities for density functional theory
复制标题

密度泛函理论中具有不确定性量化能力的交换相关函数的开发

DOI:
10.1016/j.jcp.2016.01.034
复制
发表时间:
2016
影响因子:
4.1
通讯作者:
Aldegunde M
Aldegunde M
中科院分区:
物理与天体物理2区
文献类型:
--
作者:
Aldegunde M

文献摘要

参考文献

被引文献

相似文献

本文从机器学习的角度提出了一种新的交换相关泛函。使用固体和小分子的原子化能量,我们使用贝叶斯方法训练交换增强因子的线性模型,该方法允许量化预测中的不确定性。相关向量机用于自动选择模型中最相关的项。然后,我们测试这个模型的原子化能量和散装性能。平均模型提供了一个平均的绝对误差只有0.116 eV的G2/97集的测试点,但一个更大的0.314 eV的测试固体。在体性质方面,过渡金属和单价半导体的预测具有非常低的测试误差。然而,正如预期的那样,对训练集中未表示的材料类型(如离子固体)的预测显示出更大的误差。
This paper presents the development of a new exchange–correlation functional from the point of view of machine learning. Using atomization energies of solids and small molecules, we train a linear model for the exchange enhancement factor using a Bayesian approach which allows for the quantification of uncertainties in the predictions. A relevance vector machine is used to automatically select the most relevant terms of the model. We then test this model on atomization energies and also on bulk properties. The average model provides a mean absolute error of only 0.116 eV for the test points of the G2/97 set but a larger 0.314 eV for the test solids. In terms of bulk properties, the prediction for transition metals and monovalent semiconductors has a very low test error. However, as expected, predictions for types of materials not represented in the training set such as ionic solids show much larger errors.
交换在弱相互作用系统的密度泛函理论中的作用:电子密度和相互作用能的量子蒙特卡罗分析
DOI: 10.1103/physreva.80.032504
发表时间: 2009
期刊: The Journal of chemical physics
影响因子: --
作者:
Y. Kanai;J. Grossman
通讯作者: J. Grossman
DOI: 10.1073/pnas.1423145112
发表时间: 2015-01
期刊: Proceedings of the National Academy of Sciences
影响因子: --
作者:
Jianwei Sun;J. Perdew;A. Ruzsinszky
通讯作者: Jianwei Sun;J. Perdew;A. Ruzsinszky
DOI: 10.1002/qua.560490416
发表时间: 1994
影响因子: 2.2
作者:
M. Levy;J. Perdew
通讯作者: J. Perdew